Hugging Face's logo

MagicalAlchemist
/
Apriel-1.6-15b-Thinker-R.C.1_2-Magic_decensored

Safetensors
llava
Model card Files
xet
 Community
MagicalAlchemist commited on
Commit
d5add41
·
verified ·
1 Parent(s): 7bdc358

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +173 -0
  3. config.json +170 -0
  4. generation_config.json +6 -0
  5. model-00001-of-00007.safetensors +3 -0
  6. model-00002-of-00007.safetensors +3 -0
  7. model-00003-of-00007.safetensors +3 -0
  8. model-00004-of-00007.safetensors +3 -0
  9. model-00005-of-00007.safetensors +3 -0
  10. model-00006-of-00007.safetensors +3 -0
  11. model-00007-of-00007.safetensors +3 -0
  12. model.safetensors.index.json +665 -0
  13. preprocessor_config.json +27 -0
  14. processor_config.json +35 -0
  15. special_tokens_map.json +30 -0
  16. tokenizer.json +3 -0
  17. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# ---------------------------------------------------------------------- #}
2
+ {# ƛƬ Default setup and flags #}
3
+ {# ---------------------------------------------------------------------- #}
4
+ {# FIX: Use "is defined" check BEFORE accessing the variable #}
5
+ {%- set messages = messages if (messages is defined and messages) else [] -%}
6
+ {%- set tools = tools if (tools is defined and tools) else [] -%}
7
+ {%- set add_generation_prompt = add_generation_prompt if (add_generation_prompt is defined) else false -%}
8
+ {%- set available_tool_string = '' -%}
9
+ {%- set add_tool_id = true -%}
10
+ {%- set add_thoughts = false -%} {# whether to include <thinking> reasoning blocks #}
11
+ {%- set add_generation_prompt = true -%} {# whether to emit reasoning starter before assistant response #}
12
+ {# Optional token placeholders (safe defaults) #}
13
+ {%- set bos_token = bos_token if (bos_token is defined) else '' -%}
14
+ {%- set eos_token = eos_token if (eos_token is defined) else '' -%}
15
+ {# ---------------------------------------------------------------------- #}
16
+ {# Core reasoning prompt and assistant reasoning prefix #}
17
+ {# ---------------------------------------------------------------------- #}
18
+ {%- set reasoning_prompt =
19
+ 'You are a thoughtful, systematic AI assistant from ServiceNow Language Models (SLAM) lab. '~
20
+ 'Analyze each question carefully, present your reasoning step-by-step, then provide the final '~
21
+ 'response after the marker [BEGIN FINAL RESPONSE].'
22
+ -%}
23
+ {%- set reasoning_asst_turn_start = 'Here are my reasoning steps:\n' -%}
24
+ {# ---------------------------------------------------------------------- #}
25
+ {# Tool list and tool call output format #}
26
+ {# ---------------------------------------------------------------------- #}
27
+ {%- if tools|length > 0 -%}
28
+ {%- set available_tool_string -%}
29
+ You are provided with function signatures within <available_tools></available_tools> XML tags.
30
+ You may call one or more functions to assist with the user query.
31
+ Don't make assumptions about the arguments. You should infer the argument values from previous
32
+ user responses and the system message.
33
+ Here are the available tools:
34
+ <available_tools>
35
+ {% for tool in tools %}{{ tool|string }}{% endfor %}
36
+
37
+ </available_tools>.
38
+
39
+ Return all function calls as a list of JSON objects within <tool_calls></tool_calls> XML tags.
40
+ Each JSON object should contain a function name and arguments as follows:
41
+ <tool_calls>[
42
+ {"name": <function-name-1>, "arguments": <args-dict-1>},
43
+ {"name": <function-name-2>, "arguments": <args-dict-2>},
44
+ ...
45
+ ]</tool_calls>
46
+ {%- endset -%}
47
+ {%- endif -%}
48
+ {# ---------------------------------------------------------------------- #}
49
+ {# Start system block if first message is not system #}
50
+ {# ---------------------------------------------------------------------- #}
51
+ {%- if messages|length > 0 and messages[0]['role'] != 'system' -%}
52
+ {%- if tools|length > 0 -%}
53
+ {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + available_tool_string + '\n' }}
54
+ {%- else -%}
55
+ {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' }}
56
+ {%- endif -%}
57
+ {%- endif -%}
58
+ {# ---------------------------------------------------------------------- #}
59
+ {# Iterate through messages #}
60
+ {# ---------------------------------------------------------------------- #}
61
+ {%- for message in messages -%}
62
+
63
+ {# ---------------- USER MESSAGE ---------------- #}
64
+ {%- if message['role'] == 'user' -%}
65
+ {{ '<|begin_user|>\n' }}
66
+ {%- if message['content'] is not string -%}
67
+ {%- for chunk in message['content'] -%}
68
+ {%- if chunk['type'] == 'text' -%}
69
+ {{ chunk['text'] }}
70
+ {%- elif chunk['type'] in ['image', 'image_url'] -%}
71
+ {{ '[IMG]' }}
72
+ {%- else -%}
73
+ {{ raise_exception('Unrecognized content type!') }}
74
+ {%- endif -%}
75
+ {%- endfor -%}
76
+ {%- else -%}
77
+ {{ message['content'] }}
78
+ {%- endif -%}
79
+
80
+ {# ---------------- SYSTEM MESSAGE ---------------- #}
81
+ {%- elif message['role'] == 'system' -%}
82
+ {%- set sys_content = message.get('content', '') -%}
83
+ {%- if sys_content and sys_content|length > 0 -%}
84
+ {%- if sys_content is string -%}
85
+ {%- set system_message = sys_content -%}
86
+ {%- else -%}
87
+ {%- set system_message = sys_content[0]['text'] -%}
88
+ {%- endif -%}
89
+ {%- else -%}
90
+ {%- set system_message = '' -%}
91
+ {%- endif -%}
92
+
93
+ {%- if tools|length > 0 -%}
94
+ {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + system_message + '\n' + available_tool_string + '\n' }}
95
+ {%- else -%}
96
+ {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + system_message + '\n' }}
97
+ {%- endif -%}
98
+
99
+ {# ---------------- ASSISTANT MESSAGE ---------------- #}
100
+ {%- elif message['role'] == 'assistant' -%}
101
+ {%- if loop.last -%}
102
+ {%- set add_tool_id = false -%}
103
+ {%- endif -%}
104
+
105
+ {{ '\n<|begin_assistant|>\n' }}
106
+
107
+ {%- if add_thoughts and message.get('thought') -%}
108
+ <thinking>{{ message['thought'] }}</thinking>
109
+ {%- endif -%}
110
+
111
+ {%- set asst_content = message.get('content', '') -%}
112
+ {%- if asst_content and asst_content|length > 0 -%}
113
+ {%- if asst_content is not string -%}
114
+ {%- set asst_text = asst_content[0]['text'] -%}
115
+ {%- else -%}
116
+ {%- set asst_text = asst_content -%}
117
+ {%- endif -%}
118
+ {# For historical turns (not the last), strip reasoning and keep only final response #}
119
+ {%- if not loop.last and '[BEGIN FINAL RESPONSE]' in asst_text -%}
120
+ {{- asst_text.split('[BEGIN FINAL RESPONSE]')[-1] | trim -}}
121
+ {%- else -%}
122
+ {{- asst_text -}}
123
+ {%- endif -%}
124
+ {%- elif message.get('chosen') and message['chosen']|length > 0 -%}
125
+ {{ message['chosen'][0] }}
126
+ {%- endif -%}
127
+
128
+ {# Tool call output #}
129
+ {%- set tool_calls = message.get('tool_calls', []) -%}
130
+ {%- if tool_calls and tool_calls|length > 0 -%}
131
+ {{ '\n<tool_calls>[' }}
132
+ {%- for tool_call in tool_calls -%}
133
+ {{ '{"name": "' + tool_call['function']['name'] + '", "arguments": ' + tool_call['function']['arguments']|string }}
134
+ {%- if add_tool_id == true and 'id' in tool_call -%}
135
+ {{ ', "id": "' + tool_call['id'] + '"' }}
136
+ {%- endif -%}
137
+ {{ '}' }}
138
+ {%- if not loop.last -%}{{ ', ' }}{%- endif -%}
139
+ {%- endfor -%}
140
+ {{ ']</tool_calls>' }}
141
+ {%- endif -%}
142
+
143
+ {%- set training_prompt = training_prompt if (training_prompt is defined) else false -%}
144
+ {%- if not loop.last or training_prompt -%}
145
+ {{ '\n<|end|>\n' }}
146
+ {%- endif -%}
147
+
148
+ {# ---------------- TOOL RESULT MESSAGE ---------------- #}
149
+ {%- elif message['role'] == 'tool' -%}
150
+ {%- set tool_content = message.get('content', '') -%}
151
+ {%- if tool_content is string -%}
152
+ {%- set tool_message = tool_content -%}
153
+ {%- else -%}
154
+ {%- set tool_message = tool_content[0]['text'] if tool_content else '' -%}
155
+ {%- endif -%}
156
+ {{ '<|begin_tool_result|>\n' + tool_message|string + '\n' }}
157
+
158
+ {# ---------------- CONTENT MESSAGE ---------------- #}
159
+ {%- elif message['role'] == 'content' -%}
160
+ {%- set msg_content = message.get('content', '') -%}
161
+ {%- if msg_content is not string -%}
162
+ {{ '<|begin_content|>\n' + msg_content[0]['text'] + '\n' }}
163
+ {%- else -%}
164
+ {{ '<|begin_content|>\n' + msg_content + '\n' }}
165
+ {%- endif -%}
166
+ {%- endif -%}
167
+
168
+ {# ---------------- REASONING PROMPT BEFORE NEXT ASSISTANT ---------------- #}
169
+ {%- if loop.last and add_generation_prompt and message['role'] != 'assistant' -%}
170
+ {{ '\n<|begin_assistant|>\n' + reasoning_asst_turn_start }}
171
+ {%- endif -%}
172
+
173
+ {%- endfor -%}
config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "ignore_index": -100,
6
+ "image_seq_length": 1,
7
+ "image_token_index": 10,
8
+ "model_type": "llava",
9
+ "multimodal_projector_bias": true,
10
+ "projector_hidden_act": "gelu",
11
+ "text_config": {
12
+ "_attn_implementation_autoset": false,
13
+ "_name_or_path": "",
14
+ "add_cross_attention": false,
15
+ "architectures": null,
16
+ "attention_dropout": 0.0,
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": 1,
20
+ "chunk_size_feed_forward": 0,
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": null,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "head_dim": 128,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 5120,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 14336,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 262400,
50
+ "min_length": 0,
51
+ "model_type": "mistral",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 32,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 48,
57
+ "num_key_value_heads": 8,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": null,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "rms_norm_eps": 1e-05,
71
+ "rope_theta": 1000000000.0,
72
+ "sep_token_id": null,
73
+ "sliding_window": null,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": false,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": "bfloat16",
84
+ "torchscript": false,
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "use_cache": true,
88
+ "vocab_size": 131072
89
+ },
90
+ "torch_dtype": "bfloat16",
91
+ "transformers_version": "4.49.0",
92
+ "vision_config": {
93
+ "_attn_implementation_autoset": false,
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": null,
97
+ "attention_dropout": 0.0,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "diversity_penalty": 0.0,
105
+ "do_sample": false,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": null,
109
+ "exponential_decay_length_penalty": null,
110
+ "finetuning_task": null,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "head_dim": 64,
114
+ "hidden_act": "silu",
115
+ "hidden_size": 1024,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "image_size": 1024,
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 4096,
123
+ "is_decoder": false,
124
+ "is_encoder_decoder": false,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "min_length": 0,
132
+ "model_type": "pixtral",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 16,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_channels": 3,
138
+ "num_hidden_layers": 24,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": null,
144
+ "patch_size": 16,
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "rope_theta": 10000.0,
153
+ "sep_token_id": null,
154
+ "suppress_tokens": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": true,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": "bfloat16",
164
+ "torchscript": false,
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ },
168
+ "vision_feature_layer": -1,
169
+ "vision_feature_select_strategy": "full"
170
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "5.3.0"
6
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b28448655e8eada1e75c93a96240b509f11f8864b7a96ab1e2a93240b0ff327
3
+ size 4865489896
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e4510dad43da1d8ad30c6dda8e1c819f08a99f8702d58c6163d6671a90ef5c
3
+ size 4907530616
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795827ca22fd7c2fd8625475119ec71fc54e384525dc240600786c099f0fd5d3
3
+ size 4907530680
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1aa07366c1eece355724bcc8ad5879ec1b7e1dd452f84706d3197f9b97de964
3
+ size 4907530680
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a9fec256ae8e7fe35a4e7082ef94f81d09d1506808b06d5e84d88a546e671a
3
+ size 4907530680
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f3f3c2b141ecf3dd7452059c22cd12dc0b36ad16442e08c83cf7b75033527b
3
+ size 4999373152
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc83b277c88fdf7ba7098b11822564812d8e19dad589a225ead95afedcd29cb3
3
+ size 232820864
model.safetensors.index.json ADDED
@@ -0,0 +1,665 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 14863859712,
4
+ "total_size": 29727719424
5
+ },
6
+ "weight_map": {
7
+ "language_model.lm_head.weight": "model-00001-of-00007.safetensors",
8
+ "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
15
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
17
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
18
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
19
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
20
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
21
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
22
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
23
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
24
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
25
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
26
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
27
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
28
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
29
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
30
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
31
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
32
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
33
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
34
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
35
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
36
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
37
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
38
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
39
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
40
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
41
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
42
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
43
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
44
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
45
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
46
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
47
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
48
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
49
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
50
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
51
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
52
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
53
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
54
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
55
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
56
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
57
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
58
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
59
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
60
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
61
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
62
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
63
+ "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
64
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
65
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
66
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
67
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
68
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
69
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
70
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
71
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
72
+ "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
73
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
74
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
75
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
76
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
77
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
78
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
79
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
80
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
81
+ "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
82
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
83
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
84
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
85
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
86
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
87
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
88
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
89
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
90
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
91
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
92
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
93
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
94
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
95
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
96
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
97
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
98
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
99
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
100
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
101
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
102
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
103
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
104
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
105
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
106
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
107
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
108
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
109
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
110
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
111
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
112
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
113
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
114
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
115
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
116
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
117
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
118
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
119
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
120
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
121
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
122
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
123
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
124
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
125
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
126
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
127
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
128
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
129
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
130
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
131
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
132
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
133
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
134
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
135
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
136
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
137
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
138
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
139
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
140
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
141
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
142
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
143
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
144
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
145
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
146
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
147
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
148
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
149
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
150
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
151
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
152
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
153
+ "language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
154
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
155
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
156
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
157
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
158
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
159
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
160
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
161
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
162
+ "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
163
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
164
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
165
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
166
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
167
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
168
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
169
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
170
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
171
+ "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
172
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
173
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
174
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
175
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
176
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
177
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
178
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
179
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
180
+ "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
181
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
182
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
183
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
184
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
185
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
186
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
187
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
188
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
189
+ "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
190
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
191
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
192
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
193
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
194
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
195
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
196
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
197
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
198
+ "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
199
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
200
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
201
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
202
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
203
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
204
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
205
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
206
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
207
+ "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
208
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
209
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
210
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
211
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
212
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
213
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
214
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
215
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
216
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
217
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
218
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
219
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
220
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
221
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
222
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
223
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
224
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
225
+ "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
226
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
227
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
228
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
229
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
230
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
231
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
232
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
233
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
234
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
235
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
236
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
237
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
238
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
239
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
240
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
241
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
242
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
243
+ "language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
244
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
245
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
246
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
247
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
248
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
249
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
250
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
251
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
252
+ "language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
253
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
254
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
255
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
256
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
257
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
258
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
259
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
260
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
261
+ "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
262
+ "language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
263
+ "language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
264
+ "language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
265
+ "language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
266
+ "language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
267
+ "language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
268
+ "language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
269
+ "language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
270
+ "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
271
+ "language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
272
+ "language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
273
+ "language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
274
+ "language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
275
+ "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
276
+ "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
277
+ "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
278
+ "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
279
+ "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
280
+ "language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
281
+ "language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
282
+ "language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
283
+ "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
284
+ "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
285
+ "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
286
+ "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
287
+ "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
288
+ "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
289
+ "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
290
+ "language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
291
+ "language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
292
+ "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
293
+ "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
294
+ "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
295
+ "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
296
+ "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
297
+ "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
298
+ "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
299
+ "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
300
+ "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
301
+ "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
302
+ "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
303
+ "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
304
+ "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
305
+ "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
306
+ "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
307
+ "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
308
+ "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
309
+ "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
310
+ "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
311
+ "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
312
+ "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
313
+ "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
314
+ "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
315
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
316
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
317
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
318
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
319
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
320
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
321
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
322
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
323
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
324
+ "language_model.model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
325
+ "language_model.model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
326
+ "language_model.model.layers.40.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
327
+ "language_model.model.layers.40.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
328
+ "language_model.model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
329
+ "language_model.model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
330
+ "language_model.model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
331
+ "language_model.model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
332
+ "language_model.model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
333
+ "language_model.model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors",
334
+ "language_model.model.layers.41.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
335
+ "language_model.model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
336
+ "language_model.model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
337
+ "language_model.model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
338
+ "language_model.model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
339
+ "language_model.model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
340
+ "language_model.model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
341
+ "language_model.model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
342
+ "language_model.model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
343
+ "language_model.model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
344
+ "language_model.model.layers.42.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
345
+ "language_model.model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
346
+ "language_model.model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
347
+ "language_model.model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
348
+ "language_model.model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
349
+ "language_model.model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
350
+ "language_model.model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
351
+ "language_model.model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
352
+ "language_model.model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
353
+ "language_model.model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
354
+ "language_model.model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
355
+ "language_model.model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
356
+ "language_model.model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
357
+ "language_model.model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
358
+ "language_model.model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
359
+ "language_model.model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
360
+ "language_model.model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
361
+ "language_model.model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
362
+ "language_model.model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
363
+ "language_model.model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
364
+ "language_model.model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
365
+ "language_model.model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
366
+ "language_model.model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
367
+ "language_model.model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
368
+ "language_model.model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
369
+ "language_model.model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
370
+ "language_model.model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
371
+ "language_model.model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
372
+ "language_model.model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
373
+ "language_model.model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
374
+ "language_model.model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
375
+ "language_model.model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
376
+ "language_model.model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
377
+ "language_model.model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
378
+ "language_model.model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
379
+ "language_model.model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
380
+ "language_model.model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
381
+ "language_model.model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
382
+ "language_model.model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
383
+ "language_model.model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
384
+ "language_model.model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
385
+ "language_model.model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
386
+ "language_model.model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
387
+ "language_model.model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
388
+ "language_model.model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
389
+ "language_model.model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
390
+ "language_model.model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
391
+ "language_model.model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
392
+ "language_model.model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
393
+ "language_model.model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
394
+ "language_model.model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
395
+ "language_model.model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
396
+ "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
397
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
398
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
399
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
400
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
401
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
402
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
403
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
404
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
405
+ "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
406
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
407
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
408
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
409
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
410
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
411
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
412
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
413
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
414
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
415
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
416
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
417
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
418
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
419
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
420
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
421
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
422
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
423
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
424
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
425
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
426
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
427
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
428
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
429
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
430
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
431
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
432
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
433
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
434
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
435
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
436
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
437
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
438
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
439
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
440
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
441
+ "language_model.model.norm.weight": "model-00006-of-00007.safetensors",
442
+ "multi_modal_projector.linear_1.bias": "model-00006-of-00007.safetensors",
443
+ "multi_modal_projector.linear_1.weight": "model-00006-of-00007.safetensors",
444
+ "multi_modal_projector.linear_2.bias": "model-00006-of-00007.safetensors",
445
+ "multi_modal_projector.linear_2.weight": "model-00006-of-00007.safetensors",
446
+ "vision_tower.ln_pre.weight": "model-00006-of-00007.safetensors",
447
+ "vision_tower.patch_conv.weight": "model-00006-of-00007.safetensors",
448
+ "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00006-of-00007.safetensors",
449
+ "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00006-of-00007.safetensors",
450
+ "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00006-of-00007.safetensors",
451
+ "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00006-of-00007.safetensors",
452
+ "vision_tower.transformer.layers.0.attention_norm.weight": "model-00006-of-00007.safetensors",
453
+ "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
454
+ "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
455
+ "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
456
+ "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00006-of-00007.safetensors",
457
+ "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00006-of-00007.safetensors",
458
+ "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00006-of-00007.safetensors",
459
+ "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00006-of-00007.safetensors",
460
+ "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00006-of-00007.safetensors",
461
+ "vision_tower.transformer.layers.1.attention_norm.weight": "model-00006-of-00007.safetensors",
462
+ "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
463
+ "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
464
+ "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
465
+ "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00006-of-00007.safetensors",
466
+ "vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00006-of-00007.safetensors",
467
+ "vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00006-of-00007.safetensors",
468
+ "vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00006-of-00007.safetensors",
469
+ "vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00006-of-00007.safetensors",
470
+ "vision_tower.transformer.layers.10.attention_norm.weight": "model-00006-of-00007.safetensors",
471
+ "vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
472
+ "vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
473
+ "vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
474
+ "vision_tower.transformer.layers.10.ffn_norm.weight": "model-00006-of-00007.safetensors",
475
+ "vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00006-of-00007.safetensors",
476
+ "vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00006-of-00007.safetensors",
477
+ "vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00006-of-00007.safetensors",
478
+ "vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00006-of-00007.safetensors",
479
+ "vision_tower.transformer.layers.11.attention_norm.weight": "model-00006-of-00007.safetensors",
480
+ "vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
481
+ "vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
482
+ "vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
483
+ "vision_tower.transformer.layers.11.ffn_norm.weight": "model-00006-of-00007.safetensors",
484
+ "vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00006-of-00007.safetensors",
485
+ "vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00006-of-00007.safetensors",
486
+ "vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00006-of-00007.safetensors",
487
+ "vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00006-of-00007.safetensors",
488
+ "vision_tower.transformer.layers.12.attention_norm.weight": "model-00006-of-00007.safetensors",
489
+ "vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
490
+ "vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
491
+ "vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
492
+ "vision_tower.transformer.layers.12.ffn_norm.weight": "model-00006-of-00007.safetensors",
493
+ "vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00006-of-00007.safetensors",
494
+ "vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00006-of-00007.safetensors",
495
+ "vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00006-of-00007.safetensors",
496
+ "vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00006-of-00007.safetensors",
497
+ "vision_tower.transformer.layers.13.attention_norm.weight": "model-00006-of-00007.safetensors",
498
+ "vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
499
+ "vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
500
+ "vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
501
+ "vision_tower.transformer.layers.13.ffn_norm.weight": "model-00006-of-00007.safetensors",
502
+ "vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00006-of-00007.safetensors",
503
+ "vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00006-of-00007.safetensors",
504
+ "vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00006-of-00007.safetensors",
505
+ "vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00006-of-00007.safetensors",
506
+ "vision_tower.transformer.layers.14.attention_norm.weight": "model-00006-of-00007.safetensors",
507
+ "vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
508
+ "vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
509
+ "vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
510
+ "vision_tower.transformer.layers.14.ffn_norm.weight": "model-00006-of-00007.safetensors",
511
+ "vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00006-of-00007.safetensors",
512
+ "vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00006-of-00007.safetensors",
513
+ "vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00006-of-00007.safetensors",
514
+ "vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00006-of-00007.safetensors",
515
+ "vision_tower.transformer.layers.15.attention_norm.weight": "model-00006-of-00007.safetensors",
516
+ "vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
517
+ "vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
518
+ "vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
519
+ "vision_tower.transformer.layers.15.ffn_norm.weight": "model-00006-of-00007.safetensors",
520
+ "vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00006-of-00007.safetensors",
521
+ "vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00006-of-00007.safetensors",
522
+ "vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00006-of-00007.safetensors",
523
+ "vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00006-of-00007.safetensors",
524
+ "vision_tower.transformer.layers.16.attention_norm.weight": "model-00006-of-00007.safetensors",
525
+ "vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
526
+ "vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
527
+ "vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
528
+ "vision_tower.transformer.layers.16.ffn_norm.weight": "model-00006-of-00007.safetensors",
529
+ "vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00006-of-00007.safetensors",
530
+ "vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00007-of-00007.safetensors",
531
+ "vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00007-of-00007.safetensors",
532
+ "vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00007-of-00007.safetensors",
533
+ "vision_tower.transformer.layers.17.attention_norm.weight": "model-00007-of-00007.safetensors",
534
+ "vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00007-of-00007.safetensors",
535
+ "vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00007-of-00007.safetensors",
536
+ "vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00007-of-00007.safetensors",
537
+ "vision_tower.transformer.layers.17.ffn_norm.weight": "model-00007-of-00007.safetensors",
538
+ "vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00007-of-00007.safetensors",
539
+ "vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00007-of-00007.safetensors",
540
+ "vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00007-of-00007.safetensors",
541
+ "vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00007-of-00007.safetensors",
542
+ "vision_tower.transformer.layers.18.attention_norm.weight": "model-00007-of-00007.safetensors",
543
+ "vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00007-of-00007.safetensors",
544
+ "vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00007-of-00007.safetensors",
545
+ "vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00007-of-00007.safetensors",
546
+ "vision_tower.transformer.layers.18.ffn_norm.weight": "model-00007-of-00007.safetensors",
547
+ "vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00007-of-00007.safetensors",
548
+ "vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00007-of-00007.safetensors",
549
+ "vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00007-of-00007.safetensors",
550
+ "vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00007-of-00007.safetensors",
551
+ "vision_tower.transformer.layers.19.attention_norm.weight": "model-00007-of-00007.safetensors",
552
+ "vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00007-of-00007.safetensors",
553
+ "vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00007-of-00007.safetensors",
554
+ "vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00007-of-00007.safetensors",
555
+ "vision_tower.transformer.layers.19.ffn_norm.weight": "model-00007-of-00007.safetensors",
556
+ "vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00006-of-00007.safetensors",
557
+ "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00006-of-00007.safetensors",
558
+ "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00006-of-00007.safetensors",
559
+ "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00006-of-00007.safetensors",
560
+ "vision_tower.transformer.layers.2.attention_norm.weight": "model-00006-of-00007.safetensors",
561
+ "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
562
+ "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
563
+ "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
564
+ "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00006-of-00007.safetensors",
565
+ "vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00007-of-00007.safetensors",
566
+ "vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00007-of-00007.safetensors",
567
+ "vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00007-of-00007.safetensors",
568
+ "vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00007-of-00007.safetensors",
569
+ "vision_tower.transformer.layers.20.attention_norm.weight": "model-00007-of-00007.safetensors",
570
+ "vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00007-of-00007.safetensors",
571
+ "vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00007-of-00007.safetensors",
572
+ "vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00007-of-00007.safetensors",
573
+ "vision_tower.transformer.layers.20.ffn_norm.weight": "model-00007-of-00007.safetensors",
574
+ "vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00007-of-00007.safetensors",
575
+ "vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00007-of-00007.safetensors",
576
+ "vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00007-of-00007.safetensors",
577
+ "vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00007-of-00007.safetensors",
578
+ "vision_tower.transformer.layers.21.attention_norm.weight": "model-00007-of-00007.safetensors",
579
+ "vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00007-of-00007.safetensors",
580
+ "vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00007-of-00007.safetensors",
581
+ "vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00007-of-00007.safetensors",
582
+ "vision_tower.transformer.layers.21.ffn_norm.weight": "model-00007-of-00007.safetensors",
583
+ "vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00007-of-00007.safetensors",
584
+ "vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00007-of-00007.safetensors",
585
+ "vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00007-of-00007.safetensors",
586
+ "vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00007-of-00007.safetensors",
587
+ "vision_tower.transformer.layers.22.attention_norm.weight": "model-00007-of-00007.safetensors",
588
+ "vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00007-of-00007.safetensors",
589
+ "vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00007-of-00007.safetensors",
590
+ "vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00007-of-00007.safetensors",
591
+ "vision_tower.transformer.layers.22.ffn_norm.weight": "model-00007-of-00007.safetensors",
592
+ "vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00007-of-00007.safetensors",
593
+ "vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00007-of-00007.safetensors",
594
+ "vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00007-of-00007.safetensors",
595
+ "vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00007-of-00007.safetensors",
596
+ "vision_tower.transformer.layers.23.attention_norm.weight": "model-00007-of-00007.safetensors",
597
+ "vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00007-of-00007.safetensors",
598
+ "vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00007-of-00007.safetensors",
599
+ "vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00007-of-00007.safetensors",
600
+ "vision_tower.transformer.layers.23.ffn_norm.weight": "model-00007-of-00007.safetensors",
601
+ "vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00006-of-00007.safetensors",
602
+ "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00006-of-00007.safetensors",
603
+ "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00006-of-00007.safetensors",
604
+ "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00006-of-00007.safetensors",
605
+ "vision_tower.transformer.layers.3.attention_norm.weight": "model-00006-of-00007.safetensors",
606
+ "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
607
+ "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
608
+ "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
609
+ "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00006-of-00007.safetensors",
610
+ "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00006-of-00007.safetensors",
611
+ "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00006-of-00007.safetensors",
612
+ "vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00006-of-00007.safetensors",
613
+ "vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00006-of-00007.safetensors",
614
+ "vision_tower.transformer.layers.4.attention_norm.weight": "model-00006-of-00007.safetensors",
615
+ "vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
616
+ "vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
617
+ "vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
618
+ "vision_tower.transformer.layers.4.ffn_norm.weight": "model-00006-of-00007.safetensors",
619
+ "vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00006-of-00007.safetensors",
620
+ "vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00006-of-00007.safetensors",
621
+ "vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00006-of-00007.safetensors",
622
+ "vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00006-of-00007.safetensors",
623
+ "vision_tower.transformer.layers.5.attention_norm.weight": "model-00006-of-00007.safetensors",
624
+ "vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
625
+ "vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
626
+ "vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
627
+ "vision_tower.transformer.layers.5.ffn_norm.weight": "model-00006-of-00007.safetensors",
628
+ "vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00006-of-00007.safetensors",
629
+ "vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00006-of-00007.safetensors",
630
+ "vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00006-of-00007.safetensors",
631
+ "vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00006-of-00007.safetensors",
632
+ "vision_tower.transformer.layers.6.attention_norm.weight": "model-00006-of-00007.safetensors",
633
+ "vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
634
+ "vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
635
+ "vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
636
+ "vision_tower.transformer.layers.6.ffn_norm.weight": "model-00006-of-00007.safetensors",
637
+ "vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00006-of-00007.safetensors",
638
+ "vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00006-of-00007.safetensors",
639
+ "vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00006-of-00007.safetensors",
640
+ "vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00006-of-00007.safetensors",
641
+ "vision_tower.transformer.layers.7.attention_norm.weight": "model-00006-of-00007.safetensors",
642
+ "vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
643
+ "vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
644
+ "vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
645
+ "vision_tower.transformer.layers.7.ffn_norm.weight": "model-00006-of-00007.safetensors",
646
+ "vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00006-of-00007.safetensors",
647
+ "vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00006-of-00007.safetensors",
648
+ "vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00006-of-00007.safetensors",
649
+ "vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00006-of-00007.safetensors",
650
+ "vision_tower.transformer.layers.8.attention_norm.weight": "model-00006-of-00007.safetensors",
651
+ "vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
652
+ "vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
653
+ "vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
654
+ "vision_tower.transformer.layers.8.ffn_norm.weight": "model-00006-of-00007.safetensors",
655
+ "vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00006-of-00007.safetensors",
656
+ "vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00006-of-00007.safetensors",
657
+ "vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00006-of-00007.safetensors",
658
+ "vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00006-of-00007.safetensors",
659
+ "vision_tower.transformer.layers.9.attention_norm.weight": "model-00006-of-00007.safetensors",
660
+ "vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00006-of-00007.safetensors",
661
+ "vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00006-of-00007.safetensors",
662
+ "vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00006-of-00007.safetensors",
663
+ "vision_tower.transformer.layers.9.ffn_norm.weight": "model-00006-of-00007.safetensors"
664
+ }
665
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "PixtralImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "patch_size": {
18
+ "height": 16,
19
+ "width": 16
20
+ },
21
+ "processor_class": "PixtralProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 1024
26
+ }
27
+ }
processor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_break_token": "[IMG_BREAK]",
3
+ "image_end_token": "[IMG_END]",
4
+ "image_processor": {
5
+ "data_format": "channels_first",
6
+ "do_convert_rgb": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.48145466,
12
+ 0.4578275,
13
+ 0.40821073
14
+ ],
15
+ "image_processor_type": "PixtralImageProcessorFast",
16
+ "image_std": [
17
+ 0.26862954,
18
+ 0.26130258,
19
+ 0.27577711
20
+ ],
21
+ "patch_size": {
22
+ "height": 16,
23
+ "width": 16
24
+ },
25
+ "resample": 3,
26
+ "rescale_factor": 0.00392156862745098,
27
+ "size": {
28
+ "longest_edge": 1024
29
+ }
30
+ },
31
+ "image_token": "[IMG]",
32
+ "patch_size": 16,
33
+ "processor_class": "PixtralProcessor",
34
+ "spatial_merge_size": 1
35
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c4196bd3d61abf4a6f9d116435140b8ac0606e15eb4d02e235f9036257dc3e
3
+ size 17077327
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff